Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

UMAX (vector, 4H)

Test 1: uops

Code:

  umax v0.4h, v0.4h, v1.4h
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03181e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150126116872510001000100026468012018203720371572318951000100020002037203711100110002073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100001873116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160126116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  umax v0.4h, v0.4h, v1.4h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000006119687251010010010000121100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071031622197910100001002003820038200382003820038
1020420037149000048061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020085200372110201100991001001000010000069071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
1020420037150000000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000198071021622197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000021071021622197910100001002003820038200382003820038
102042003715000000025119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000001206119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000006071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371500000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000006071021622197910100001002003820038200382003820038
10204200371500000002511968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000147071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150004061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001020000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010030000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768020018200372003718444031876710010201000020200002003720037111002110910101000010024000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001003000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037149000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844403187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
1002420037150000061196872510010101000010100005028476802001820037200371844403187671001020100002020356200372003711100211091010100001000000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  umax v0.4h, v1.4h, v0.4h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001387102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100207102162219791100001002003820038200382003820038
1020420037150025119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100207102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100207102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100207102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150025119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100207102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100607102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100407102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000660640216221978510000102003820038200382003820038
1002420037150010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119676441001010100001010000502847680020018200652003718444318767100102010000202000020037200371110021109101010000101000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150072619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001050000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001053000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  umax v0.4h, v8.4h, v9.4h
  umax v1.4h, v8.4h, v9.4h
  umax v2.4h, v8.4h, v9.4h
  umax v3.4h, v8.4h, v9.4h
  umax v4.4h, v8.4h, v9.4h
  umax v5.4h, v8.4h, v9.4h
  umax v6.4h, v8.4h, v9.4h
  umax v7.4h, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)0308090b191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000100511041632200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511031632200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511031632200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000030511031633200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511031633200350800001002003920039201912003920039
802042003815000000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010005300511031632200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511031632200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511031632200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000030511031623200350800001002003920039200392003920039
80204200381500000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511021623200350800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)0318191e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)6061696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd0d2d5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150008971152580010108000010800005064000010200192003820038999603100188001020800002016000020038200381180021109101080000100050200013160012102003580000102003920039200392023520039
800242003815000070258001010800001080000506400001020019200382003899960310018800102080096201600002003820038118002110910108000010005020519160012182003580000102003920039200392003920039
80024200381500004525800101080000108000050640000102001920038200389996031001880010208000020160000200382003811800211091010800001030350200016160016132003580000102003920039200392003920039
8002420038150000392580010108000010800005064000010200192003820038999603100188001020800002016000020038200381180021109101080000100050205112160016122003580000102003920039200392003920039
8002420038150000392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100050200016160011142003580000102003920039200392003920039
800242003815000039258001010800001080000506400001520019200382003899960310018800102080000201600002003820038118002110910108000010005020009160017142003580000102003920039200392003920039
800242003815000039258001010800001080000506400000020019200382003899960310018800102080000201600002003820038118002110910108000010115650200015160013132003580000102003920039200392003920039
8002420038150000392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100050200019160011162003580000102003920039200392003920039
8002420038150000692580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100050200015160012122003580000102003920039200392003920039
8002420038150000392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100050200016160016132003580000102003920039200392003920039